RT @ycombinator: .@RelariAI just launched the AI agent builder for Software 3.0. Write specs in English. Get work….

RT @Yiszzzz: Majority of “AI Agents” advertised today aren’t really agents at all. They’re 𝐢𝐧𝐭𝐫𝐢𝐜𝐚𝐭𝐞 𝐩𝐢𝐩𝐞𝐥𝐢𝐧𝐞𝐬 𝐰𝐢𝐭𝐡 𝐝𝐞𝐭𝐞𝐫𝐦𝐢𝐧𝐢𝐬𝐭𝐢𝐜 𝐜𝐨𝐧𝐭𝐫𝐨𝐥 𝐟….

RT @Yiszzzz: How to choose the right agent framework? We built the same Agentic Finance App using LangGraph, CrewAI, and OpenAI Swarm and h….

RT @Yiszzzz: Join me at this webinar next week! .@qdrant_engine @RelariAI.

RT @Yiszzzz: I was inspired by the SF breakfasts hosted by @Inferless_ and started organizing "GenAI Developer Breakfast" at Harvard Square….

RT @moreisdifferent: PSA for Boston area folks: . I'm pleased to announce the speaker lineup for the June @aicampai Boston meetup. Next Tue….

RT @_odsc: Are you getting the most out of your LLMs and RAGs? In the latest episode of the ODSC Ai X Podcast, join Pasquale Antonante, PhD….

RT @zilliz_universe: .@Yiszzzz from @RelariAI gave a community talk about how to get the GenAI apps from demo to production. (hint: synthet….

RT @Yiszzzz: Giving a talk on synthetic data using @RelariAI tomorrow alongside folks from @milvusio, @TectonAI, and @bentomlai. Come join….

🙌 We're excited to collaborate with @milvusio on this case study! Our synthetic data pipeline has been integrated with the new lightweight Milvus Lite vector database released today!.

Check out our latest case study:.1️⃣ Generate Synthetic Dataset.2️⃣ Systematically benchmark 3 RAG systems with the synthetic dataset.

RT @tryfondo: 🚀@RelariAI launched! Testing and Simulation Stack for GenAI Apps . "Harden your GenAI Systems with Synthetic Data". 🌐 https:/….

💡 All is packaged in a new, simpler API that makes it easier to use. Check out the latest version (0.3.9) and let us know what you think! . We leveraged sqlglot in these metrics, thanks @captaintobs for the amazing package!.

We added two deterministic SQL metrics to help you evaluate text-to-SQL applications. These metrics understand the database schema and interpret the semantics of the generated query to give you a score you can trust.

Text-to-SQL is one of the most common LLM applications, but it is a complex task. Human language is inherently ambiguous and understanding large databases is challenging.

🚀 Continuous-Eval has now (deterministic!) text-to-SQL metrics!

RT @_odsc: Here's a novel approach to use production data to simulate user feedback for testing and evaluating your LLM app. @RelariAI htt….

RT @_odsc: In this blog, we will walk through the popular topic synthetic data in the context of LLM testing and evaluation. @RelariAI http….

RT @Yiszzzz: Curious about generating synthetic data for RAG and AI agents? Check out the latest blog from us @AntonanteP @RelariAI .https:….

RT @Yiszzzz: If you missed @AntonanteP's talk @_odsc last week on 3 pillars of good LLM evaluation, please DM us and we are happy to share….